errorplot.py 文件源码

def plot_difference_histogram(group, gene_name, bins=np.arange(20.1)):
    """
    Plot a histogram of percentage differences for a specific gene.
    """
    exact_matches = group[group.V_SHM == 0]
    CDR3s_exact = len(set(s for s in exact_matches.CDR3_nt if s))
    Js_exact = len(set(exact_matches.J_gene))

    fig = Figure(figsize=(100/25.4, 60/25.4))
    ax = fig.gca()
    ax.set_xlabel('Percentage difference')
    ax.set_ylabel('Frequency')
    fig.suptitle('Gene ' + gene_name, y=1.08, fontsize=16)
    ax.set_title('{:,} sequences assigned'.format(len(group)))

    ax.text(0.25, 0.95,
        '{:,} ({:.1%}) exact matches\n  {} unique CDR3\n  {} unique J'.format(
            len(exact_matches), len(exact_matches) / len(group),
            CDR3s_exact, Js_exact),
        transform=ax.transAxes, fontsize=10,
        bbox=dict(boxstyle='round', facecolor='white', alpha=0.5),
        horizontalalignment='left', verticalalignment='top')
    _ = ax.hist(list(group.V_SHM), bins=bins)
    return fig